© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129026
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     last
    -1.55
     "";
    -1.50
     sebag
    -1.33
     nią
    -1.31
     motyw
    -1.30
     innymi
    -1.30
    一旁
    -1.29
     donnant
    -1.29
     debit
    -1.28
     następnie
    -1.28
    POSITIVE LOGITS
     It
    1.75
     This
    1.54
     یکی
    1.53
    Один
    1.52
    Variante
    1.47
     alltid
    1.45
     preferências
    1.45
     they
    1.45
     unſ
    1.41
    是
    1.40
    Activations Density 0.076%

    No Known Activations